aboutsummaryrefslogtreecommitdiffstats
Commit message (Collapse)AuthorAgeFilesLines
* Merge pull request #8814 from catboxanon/inpaint-maskAUTOMATIC11112023-03-252-0/+20
|\ | | | | Add ability to display and/or save inpainting mask and masked composite
| * Expose inpainting mask and compositecatboxanon2023-03-222-0/+20
| | | | | | | | | | | | For inpainting, this exposes the mask and masked composite and gives the user the ability to display these in the web UI, save to disk, or both.
* | Merge pull request #8651 from vladmandic/flickerAUTOMATIC11112023-03-251-0/+3
|\ \ | | | | | | disable gradio css transitions
| * | disable gradio css transitionsVladimir Mandic2023-03-151-0/+3
| |/
* | Merge pull request #8824 from zimkjh/fix-variable-typoAUTOMATIC11112023-03-251-2/+2
|\ \ | | | | | | fix variable typo
| * | fix variable typocarat-johyun2023-03-231-2/+2
| |/
* | Merge pull request #8647 from Tps-F/add_submoduleAUTOMATIC11112023-03-251-8/+5
|\ \ | | | | | | Support git submodule for extension and Fix Windows PermissionError
| * | Delete settings.jsonFtps2023-03-161-0/+0
| | |
| * | Cross device linkFtps2023-03-162-1/+11
| | |
| * | remove unused libraryFtps2023-03-151-2/+0
| | | | | | | | | | | | I'm sorry I forgot.
| * | Update ui_extensions.pyFtps2023-03-151-16/+5
| |/ | | | | | | Add git submodule and Fix WinError
* | Merge pull request #8799 from JaRail/masterAUTOMATIC11112023-03-252-29/+75
|\ \ | | | | | | Loopback Script Updates
| * | Fix "masked content" in loopback scriptJames Railton2023-03-231-0/+4
| | | | | | | | | | | | | | | | | | The loopback script did not set masked content to original after first loop. So each loop would apply a fill, or latent mask. This would essentially reset progress each loop. The desired behavior is to use the mask for the first loop, then continue to iterate on the results of the previous loop.
| * | Loopback Script UpdatesJames Railton2023-03-222-30/+72
| |/ | | | | | | | | | | | | | | - Improved user experience. You can now pick the denoising strength of the final loop and one of three curves. Previously you picked a multiplier such as 0.98 or 1.03 to define the change to the denoising strength for each loop. You had to do a ton of math in your head to visualize what was happening. The new UX makes it very easy to understand what's going on and tweak. - For batch sizes over 1, intermediate images no longer returned. For a batch size of 1, intermediate images from each loop will continue to be returned. When more than 1 image is returned, a grid will also be generated. Previously for larger jobs, you'd get back a mess of many grids and potentially hundreds of images with no organization. To make large jobs usable, only final images are returned. - Added support for skipping current image. Fixed interrupt to cleanly end and return images. Previously these would throw. - Improved tooltip descriptions - Fix some edge cases
* | Merge pull request #8801 from EllangoK/xyz-valuesAUTOMATIC11112023-03-251-5/+16
|\ \ | | | | | | Fixes xyz extra_generation_params not being saved (previously worked)
| * | fixes xyz extra_generation_params not being savedEllangoK2023-03-221-5/+16
| |/
* | Merge pull request #8731 from jokker87/masterAUTOMATIC11112023-03-250-0/+0
|\ \ | | | | | | fixed typo in prompt-bracket-checker.js which leads to js error
| * | fixed typo in prompt-bracket-checker.js which leads to js errorMichael Bachmann2023-03-191-1/+1
| |/
* | use HTTP request to fetch metadata for Lora cards instead of including it ↵AUTOMATIC2023-03-253-12/+72
| | | | | | | | into the main page
* | Merge pull request #8878 from butaixianran/masterAUTOMATIC11112023-03-251-1/+5
|\ \ | | | | | | Fix None type error for TI module
| * | Fix None type error for TI modulebutaixianran2023-03-241-1/+5
| |/ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | When user using model_name.png as a preview image, textural_inversion.py still treat it as an embeding, and didn't handle its error, just let python throw out an None type error like following: ```bash File "D:\Work\Dev\AI\stable-diffusion-webui\modules\textual_inversion\textual_inversion.py", line 155, in load_from_file name = data.get('name', name) AttributeError: 'NoneType' object has no attribute 'get' ``` With just a simple `if data:` checking as following, there will be no error, breaks nothing, and now this module can works fine with user's preview images. Old code: ```python data = extract_image_data_embed(embed_image) name = data.get('name', name) ``` New code: ```python data = extract_image_data_embed(embed_image) if data: name = data.get('name', name) else: # if data is None, means this is not an embeding, just a preview image return ``` Also, since there is no more errors on textual inversion module, from now on, extra network can set "model_name.png" as preview image for embedings.
* | Merge pull request #8866 from brkirch/mps-torch-2-0-nn-linear-workaroundsAUTOMATIC11112023-03-252-1/+34
|\ \ | | | | | | Add PyTorch 2.0 support for macOS, fix image generation on macOS 13.2.X
| * | Add workaround for MPS layer_norm on PyTorch 2.0brkirch2023-03-241-1/+3
| | | | | | | | | | | | On PyTorch 2.0, with MPS layer_norm only accepts float32 inputs. This was fixed shortly after 2.0 was finalized so the workaround can be applied with an exact version match.
| * | Add workaround for broken nn.Linear on macOS 13.2brkirch2023-03-242-0/+31
| |/ | | | | | | Credit to danieldk (https://github.com/explosion/curated-transformers/pull/124) for the workaround this is based on.
* | Merge pull request #8782 from FNSpd/masterAUTOMATIC11112023-03-253-3/+4
|\ \ | | | | | | --upcast-sampling support for CUDA
| * | Update devices.pyFNSpd2023-03-241-1/+1
| | |
| * | Update sd_hijack_optimizations.pyFNSpd2023-03-241-1/+1
| | |
| * | Update sd_hijack_unet.pyFNSpd2023-03-241-1/+1
| | |
| * | Update lora.pyFNSpd2023-03-211-0/+1
| | |
| * | Update sd_hijack_optimizations.pyFNSpd2023-03-211-1/+1
| | |
| * | Update sd_hijack_unet.pyFNSpd2023-03-211-1/+1
| | |
| * | Update devices.pyFNSpd2023-03-211-1/+1
| |/
* | Merge branch 'gradio-3-22'AUTOMATIC2023-03-250-0/+0
|\ \
| * | fix generate forever and other context menusAUTOMATIC2023-03-251-1/+1
| | |
| * | restore interrupt/stop button stylingAUTOMATIC2023-03-251-0/+4
| | |
| * | fix clipping in lightbox image viewerAUTOMATIC2023-03-251-60/+25
| | |
| * | bump gradio to 3.23AUTOMATIC2023-03-255-5/+11
| | | | | | | | | | | | fix broken image dragging
| * | fix extra networks uiAUTOMATIC2023-03-212-4/+7
| | |
| * | enable queue by defaultAUTOMATIC2023-03-215-16/+34
| | | | | | | | | | | | more stylistic changes
| * | hide delete button for single-item dropdownAUTOMATIC2023-03-214-12/+50
| | | | | | | | | | | | more stylistic changes
| * | fix ctrl+up/down attention editAUTOMATIC2023-03-213-4/+14
| | | | | | | | | | | | | | | fix dropdown obscured by live preview stylistic changes
| * | initial gradio 3.22 supportAUTOMATIC2023-03-2015-625/+289
| | |
* | | fix generate forever and other context menusAUTOMATIC2023-03-251-1/+1
| | |
* | | restore interrupt/stop button stylingAUTOMATIC2023-03-251-0/+4
| | |
* | | fix clipping in lightbox image viewerAUTOMATIC2023-03-251-60/+25
| | |
* | | bump gradio to 3.23AUTOMATIC2023-03-255-5/+11
| | | | | | | | | | | | fix broken image dragging
* | | fix extra networks uiAUTOMATIC2023-03-252-4/+7
| | |
* | | enable queue by defaultAUTOMATIC2023-03-255-16/+34
| | | | | | | | | | | | more stylistic changes
* | | hide delete button for single-item dropdownAUTOMATIC2023-03-254-12/+50
| | | | | | | | | | | | more stylistic changes
* | | fix ctrl+up/down attention editAUTOMATIC2023-03-253-4/+14
| | | | | | | | | | | | | | | fix dropdown obscured by live preview stylistic changes
generated by cgit v1.2.3 (git 2.25.1) at 2025-05-03 12:18:24 +0000